mlsanityData to 14 Oct 2026

iNNformant: Boundary Samples as Telltale Watermarks

arXiv 2106.07303 ↗First posted 14 Jun 2021cs.LG cs.CR cs.MMcited by 3

Not on the map. Why?

Abstract (arXiv)

Boundary samples are special inputs to artificial neural networks crafted to identify the execution environment used for inference by the resulting output label. The paper presents and evaluates algorithms to generate transparent boundary samples. Transparency refers to a small perceptual distortion of the host signal (i.e., a natural input sample). For two established image classifiers, ResNet on FMNIST and CIFAR10, we show that it is possible to generate sets of boundary samples which can identify any of four tested microarchitectures. These sets can be built to not contain any sample with a worse peak signal-to-noise ratio than 70dB. We analyze the relationship between search complexity and resulting transparency.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 13 of its 25 references that are in the map. First posted on arXiv 14 Jun 2021.

Builds on

13 of 25 references.

References · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  6. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  7. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  8. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  9. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 118
  10. 2019How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNNcited by 66
  11. 2019Robust Watermarking of Neural Network with Exponential Weightingcited by 51
  12. 2021Forensicability of Deep Neural Network Inference Pipelinescited by 5
1 more
  1. 2020Towards Certifiable Adversarial Sample Detectioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Quantamination: Dynamic Quantization Leaks Your Data Across the Batchcited by 2
  2. 2026FloatDoor: Platform-Triggered Backdoors in LLMscited by 2
  3. 2026Logit Leakage through Floating-Point Bias Additioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Fragile Model Watermark for integrity protection: leveraging boundary volatility and sensitive sample-pairing
  2. 2024WAVES: Benchmarking the Robustness of Image Watermarks
  3. 2025Sequential PatchCore: Anomaly Detection for Surface Inspection using Synthetic Impurities
  4. 2025VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systems
  5. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection
  6. 2026Contour Refinement using Discrete Diffusion in Low Data Regime
  7. 2025PureSample: Neural Materials Learned by Sampling Microgeometry
  8. 2026Boundary-Aware Quantization: Finite-Scale Decision Geometry of Neural Classifiers